SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions
This work addresses the limitation of traditional knowledge graph embeddings for applications like question answering and entity classification by introducing interpretable semantic representations.
The paper tackles the problem of uninterpretable representations in knowledge graph embedding by proposing a semantic representation method that uses a two-level hierarchical generative process to assign semantic categories to triples, resulting in substantial performance improvements over state-of-the-art baselines.
Knowledge representation is an important, long-history topic in AI, and there have been a large amount of work for knowledge graph embedding which projects symbolic entities and relations into low-dimensional, real-valued vector space. However, most embedding methods merely concentrate on data fitting and ignore the explicit semantic expression, leading to uninterpretable representations. Thus, traditional embedding methods have limited potentials for many applications such as question answering, and entity classification. To this end, this paper proposes a semantic representation method for knowledge graph \textbf{(KSR)}, which imposes a two-level hierarchical generative process that globally extracts many aspects and then locally assigns a specific category in each aspect for every triple. Since both aspects and categories are semantics-relevant, the collection of categories in each aspect is treated as the semantic representation of this triple. Extensive experiments justify our model outperforms other state-of-the-art baselines substantially.